A signer-independent Arabic Sign Language recognition system using face detection, geometric features, and a Hidden Markov Model

M. Mohandes, M. Deriche*, U. Johar, S. Ilyas

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

40 Scopus citations

Abstract

In this paper, we propose an image-based system for Arabic Sign Language (ArSL) recognition. The algorithm starts by detecting the face of the signer using a Gaussian skin color model. The centroid of the detected face is then used as a reference point for tracking the hands' movements. The hands regions are segmented using a region growing algorithm assuming the signer wears a yellow and an orange colored gloves. From the segmented hands regions, an optimal set of features is extracted. To represent the time varying feature patterns, a Hidden Markov Model (HMM) is then used. Before using HMM in testing, the number of states and the number of Gaussian mixtures are optimized. The proposed system was implemented for both signer dependent and signer independent conditions. The experimental results show that an accuracy of more than 95% can be achieved with a large database of 300 signs. The results outperform previous work on ArSL mainly restricted to small vocabulary size.

Original languageEnglish
Pages (from-to)422-433
Number of pages12
JournalComputers and Electrical Engineering
Volume38
Issue number2
DOIs
StatePublished - Mar 2012

Bibliographical note

Funding Information:
The authors acknowledge the support of King Abdulaziz City of Science and Technology under Grants AT 22–89 and 22–90. The authors also acknowledge the support of King Fahd University of Petroleum & Minerals.

ASJC Scopus subject areas

  • Control and Systems Engineering
  • General Computer Science
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'A signer-independent Arabic Sign Language recognition system using face detection, geometric features, and a Hidden Markov Model'. Together they form a unique fingerprint.

Cite this